AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation

Ranked by how close their title and abstract are to this paper’s. Select some to read them together.

Closest papers

1. Very close Not relevant

   AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agents

   Jiabin Tang, Tian-Yu Fan, Chao Huang · 2025 · arXiv.org · preprint, not peer reviewed · cited 63 times · Not summarized yet

   Abstract

   Large Language Model (LLM) Agents have demonstrated remarkable capabilities in task automation and intelligent decision-making, driving the widespread adoption of agent development frameworks such as LangChain and AutoGen. However, these frameworks predominantly serve developers with extensive technical expertise - a significant limitation considering that only 0.03 % of the global population possesses the necessary programming skills. This stark accessibility gap raises a fundamental question: Can we enable everyone, regardless of technical background, to build their own LLM agents using natural language alone? To address this challenge, we introduce AutoAgent-a Fully-Automated and highly S…

2. Very close Cited by this paper Not relevant

   AutoAgents: A Framework for Automatic Agent Generation

   Guangyao Chen, Siwei Dong, Yu Shu et al. · 2023 · Artificial Intelligence · cited 321 times · AI summary available

   Abstract

   Large language models (LLMs) have enabled remarkable advances in automated task-solving with multi-agent systems. However, most existing LLM-based multi-agent approaches rely on predefined agents to handle simple tasks, limiting the adaptability of multi-agent collaboration to different scenarios. Therefore, we introduce AutoAgents, an innovative framework that adaptively generates and coordinates multiple specialized agents to build an AI team according to different tasks. Specifically, AutoAgents couples the relationship between tasks and roles by dynamically generating multiple required agents based on task content and planning solutions for the current task based on the generated expert …

3. Very close Not relevant

   AutoGenesisAgent: Self-Generating Multi-Agent Systems for Complex Tasks

   Jeremy R. Harper · 2024 · arXiv.org · preprint, not peer reviewed · cited 5 times · Not summarized yet

   Abstract

   The proliferation of large language models (LLMs) and their integration into multi-agent systems has paved the way for sophisticated automation in various domains. This paper introduces AutoGenesisAgent, a multi-agent system that autonomously designs and deploys other multi-agent systems tailored for specific tasks. AutoGenesisAgent comprises several specialized agents including System Understanding, System Design, Agent Generator, and several others that collectively manage the lifecycle of creating functional multi-agent systems from initial concept to deployment. Each agent in AutoGenesisAgent has distinct responsibilities ranging from interpreting input prompts to optimizing system perfo…

4. Very close Not relevant

   AutoFlowgen: A Multi-Agent Framework for Automated Generation of Workflows from Natural Language

   Zhongjun Yang, H. E, Zichen Tang et al. · 2025 · 2025 5th International Conference on Artificial Intelligence, Big Data and Algorithms (CAIBDA) · cited 1 time · Not summarized yet

   Abstract

   Agentic Workflows are an important application form of Large Language Models (LLMs), but automatically generating executable Agentic Workflows from natural language descriptions is a significant challenge. Directly prompting LLMs to generate complex, logically sound, and executable workflows is often ineffective due to the complexities of task decomposition, node selection, parameter configuration, and inter-node dependency management. To address these challenges, we propose AutoFlowGen, a multi-agent framework that decomposes the workflow generation task into distinct stages: requirements analysis, structural planning, sketch drafting, code generation, and reflective optimization. Each stag…

5. Very close Not relevant

   AutoGen Studio: A No-Code Developer Tool for Building and Debugging Multi-Agent Systems

   Victor Dibia, Jingya Chen, Gagan Bansal et al. · 2024 · Software Engineering · cited 46 times · AI summary available

   Abstract

   Multi-agent systems, where multiple agents (generative AI models + tools) collaborate, are emerging as an effective pattern for solving long-running, complex tasks in numerous domains. However, specifying their parameters (such as models, tools, and orchestration mechanisms etc,.) and debugging them remains challenging for most developers. To address this challenge, we present AUTOGEN STUDIO, a no-code developer tool for rapidly prototyping, debugging, and evaluating multi-agent workflows built upon the AUTOGEN framework. AUTOGEN STUDIO offers a web interface and a Python API for representing LLM-enabled agents using a declarative (JSON-based) specification. It provides an intuitive drag-and…

6. Very close Not relevant

   Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents

   Yashar Talebirad, Amirhossein Nadiri · 2023 · Artificial Intelligence · preprint, not peer reviewed · cited 509 times · AI summary available

   Abstract

   In this paper, we present a novel framework for enhancing the capabilities of large language models (LLMs) by leveraging the power of multi-agent systems. Our framework introduces a collaborative environment where multiple intelligent agent components, each with distinctive attributes and roles, work together to handle complex tasks more efficiently and effectively. We demonstrate the practicality and versatility of our framework through case studies in artificial general intelligence (AGI), specifically focusing on the Auto-GPT and BabyAGI models. We also examine the "Gorilla" model, which integrates external APIs into the LLM. Our framework addresses limitations and challenges such as loop…

7. Very close Not relevant

   EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms

   Siyu Yuan, Kaitao Song, Jiangjie Chen et al. · 2024 · Artificial Intelligence · cited 144 times · Not summarized yet

   Abstract

   The rise of powerful large language models (LLMs) has spurred a new trend in building LLM-based autonomous agents for solving complex tasks, especially multi-agent systems. Despite the remarkable progress, we notice that existing works are heavily dependent on human-designed frameworks, which greatly limits the functional scope and scalability of agent systems. How to automatically extend the specialized agent to multi-agent systems to improve task-solving capability still remains a significant challenge. In this paper, we introduce EvoAgent, a generic method to automatically extend expert agents to multi-agent systems via the evolutionary algorithm, thereby improving the effectiveness of LL…

8. Very close Not relevant

   The Role of LLM Agent Apps in Conversational AI

   Srikanth Vadlamani, Daksha Borada · 2025 · International Journal of Research in Modern Engineering & Emerging Technology · Not summarized yet

   Abstract

   The rapid growth of Large Language Models (LLMs) has tremendously boosted the strength of conversational artificial intelligence applications. In this regard, LLM agent applications have become strong tools for automating and individualizing conversations across industries such as customer service, healthcare, education, and entertainment. LLM agent applications use LLMs to have sophisticated, contextually aware conversations, thereby providing users with a natural conversational experience. Though they have great capabilities, there is a massive research gap regarding the distinctive roles and potential of LLM agent applications in improving conversational AI systems. The goal of this study…

Prior work it builds on

1. Close Not relevant

   Self-Collaboration Code Generation via ChatGPT

   Yihong Dong, Xue Jiang, Zhi Jin et al. · 2023 · ACM Transactions on Software Engineering and Methodology · cited 590 times · Not summarized yet

   Abstract

   Although large language models (LLMs) have demonstrated remarkable code-generation ability, they still struggle with complex tasks. In real-world software development, humans usually tackle complex tasks through collaborative teamwork, a strategy that significantly controls development complexity and enhances software quality. Inspired by this, we present a self-collaboration framework for code generation employing LLMs, exemplified by ChatGPT. Specifically, through role instructions, (1) Multiple LLM agents act as distinct “experts,” each responsible for a specific subtask within a complex task; (2) Specify the way to collaborate and interact, so that different roles form a virtual team to …

2. Close Not relevant

   MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework

   Sirui Hong, Mingchen Zhuge, Jonathan Chen et al. · 2023 · Artificial Intelligence · preprint, not peer reviewed · cited 2,753 times · AI summary available

   Abstract

   Remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs). Existing LLM-based multi-agent systems can already solve simple dialogue tasks. Solutions to more complex tasks, however, are complicated through logic inconsistencies due to cascading hallucinations caused by naively chaining LLMs. Here we introduce MetaGPT, an innovative meta-programming framework incorporating efficient human workflows into LLM-based multi-agent collaborations. MetaGPT encodes Standardized Operating Procedures (SOPs) into prompt sequences for more streamlined workflows, thus allowing agents with human-like domain expertise to verify intermediat…

3. Close Not relevant

   Adaptive In-conversation Team Building for Language Model Agents

   Lin-Xin Song, Jia-Le Liu, Jieyu Zhang et al. · 2024 · arXiv.org · preprint, not peer reviewed · cited 45 times · Not summarized yet

   Abstract

   Leveraging multiple large language model (LLM) agents has shown to be a promising approach for tackling complex tasks, while the effective design of multiple agents for a particular application remains an art. It is thus intriguing to answer a critical question: Given a task, how can we build a team of LLM agents to solve it effectively? Our new adaptive team-building paradigm offers a flexible solution, realized through a novel agent design named Captain Agent. It dynamically forms and manages teams for each step of a task-solving process, utilizing nested group conversations and reflection to ensure diverse expertise and prevent stereotypical outputs, allowing for a flexible yet structured…

4. Close Not relevant

   The Rise and Potential of Large Language Model Based Agents: A Survey

   Zhiheng Xi, Wenxiang Chen, Xin Guo et al. · 2023 · Artificial Intelligence · preprint, not peer reviewed · cited 2,192 times · AI summary available

   Abstract

   For a long time, humanity has pursued artificial intelligence (AI) equivalent to or surpassing the human level, with AI agents considered a promising vehicle for this pursuit. AI agents are artificial entities that sense their environment, make decisions, and take actions. Many efforts have been made to develop intelligent AI agents since the mid-20th century. However, these efforts have mainly focused on advancement in algorithms or training strategies to enhance specific capabilities or performance on particular tasks. Actually, what the community lacks is a sufficiently general and powerful model to serve as a starting point for designing AI agents that can adapt to diverse scenarios. Due…

5. Related Used in depth by this paper Not relevant

   Language Models can Solve Computer Tasks

   Geunwoo Kim, P. Baldi, Stephen Mcaleer · 2023 · Neural Information Processing Systems · cited 549 times · AI summary available

   Abstract

   Agents capable of carrying out general tasks on a computer can improve efficiency and productivity by automating repetitive tasks and assisting in complex problem-solving. Ideally, such agents should be able to solve new computer tasks presented to them through natural language commands. However, previous approaches to this problem require large amounts of expert demonstrations and task-specific reward functions, both of which are impractical for new tasks. In this work, we show that a pre-trained large language model (LLM) agent can execute computer tasks guided by natural language using a simple prompting scheme where the agent Recursively Criticizes and Improves its output (RCI). The RCI …

Papers that cite it

1. Close Not relevant

   A Multiagent-Driven Robotic AI Chemist Enabling Autonomous Chemical Research On Demand

   Tao Song, Man Luo, Xiaolong Zhang et al. · 2025 · Journal of the American Chemical Society · cited 171 times · Not summarized yet

   Abstract

   The successful integration of large language models (LLMs) into laboratory workflows has demonstrated robust capabilities in natural language processing, autonomous task execution, and collaborative problem-solving. This offers an exciting opportunity to realize the dream of autonomous chemical research on demand. Here, we report a robotic AI chemist powered by a hierarchical multiagent system, ChemAgents, based on an on-board Llama-3.1-70B LLM, capable of executing complex, multistep experiments with minimal human intervention. It operates through a Task Manager agent that interacts with human researchers and coordinates four role-specific agents─Literature Reader, Experiment Designer, Comp…

2. Close Not relevant

   Enhancing AI Systems with Agentic Workflows Patterns in Large Language Model

   Aditi Singh, Abul Ehtesham, Saket Kumar et al. · 2024 · IEEE World AI IoT Congress (AIIoT) · cited 68 times · Not summarized yet

   Abstract

   This paper explores the significant shift towards agentic workflows in the application of Large Language Models (LLMs), moving away from traditional, linear interactions between users and AI. Through a case study analysis, we highlight the effectiveness of agentic workflows, which facilitate a more dynamic and iterative engagement, in improving outcomes in tasks such as question answering, code generation or stock analysis. Central to the agentic workflow are four foundational design patterns: reflection, planning, multi-agent collaboration, and tool utilization. These components are crucial for boosting LLM productivity and enhancing performance. The study demonstrates how agentic workflows…

3. Close Not relevant

   Safe and Scalable Collaboration in Multiagent LLM Systems: A Comprehensive Review

   Elias Hossain, Md. Mehedi Hasan Nipu, Mohammad Sakib Mahmood et al. · 2026 · IEEE Transactions on Systems, Man & Cybernetics. Systems · cited 2 times · Not summarized yet

   Abstract

   Large language model (LLM)-based multiagent systems are a rapidly evolving frontier of artificial intelligence that enables complex coordination, communication, and autonomous reasoning across distributed agents. This article presents a comprehensive review of multiagent LLM ecosystems, organized around four foundational pillars: coordination strategies, communication frameworks, safety challenges, and trust and alignment mechanisms. We synthesize a range of architectural approaches to agent interaction, including shared latent representations, strategic autonomy, task decomposition, and neuro-symbolic communication protocols. We then systematically examine the critical vulnerabilities disti…

4. Close Uses this paper in depth Not relevant

   A critical assessment of the rise of agentic AI, its capabilities, task domains and open challenges

   R. U. Khan, Hanan Aljuaid, Zhang Ning · 2026 · Discover Artificial Intelligence · cited 1 time · Not summarized yet

   Abstract

   The tremendous advancement in Large Language Models (LLMs) has triggered a fundamental reorientation in AI: from basic, single-prompt-based systems to agentic systems that can perceive the world, break down problems into multiple steps, use external tools, and continuously revise the generated response through a long-range dialogue. Although such a revolution is driven by four major technologies: instruction-following models, structured tool APIs, retrieval-augmented generation, and multi-agent orchestration systems, no holistic survey of this emergent field from a task-oriented unified point of view exists. We bridge this gap through a comprehensive survey of agentic AI systems structured b…

5. Close Not relevant

   AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges

   Ranjan Sapkota, Konstantinos I. Roumeliotis, Manoj Karkee · 2025 · Information Fusion · cited 297 times · AI summary available

   Abstract

   Information fusion, in the context of the Generative AI era, must distinguish AI Agents from Agentic AI. This review critically distinguishes between AI Agents and Agentic AI, offering a structured, conceptual taxonomy, application mapping, and analysis of opportunities and challenges to clarify their divergent design philosophies and capabilities. We begin by outlining the search strategy and foundational definitions, characterizing AI Agents as modular systems driven and enabled by LLMs and LIMs for task-specific automation. Generative AI is positioned as a precursor providing the foundation, with AI agents advancing through tool integration, prompt engineering, and reasoning enhancements.…